Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 7350
    Prev
    Next
    INDEX
    Explanations

    conditional and instructional phrases related to decision-making and options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quidem
    -0.36
     enfans
    -0.35
    ฬ
    -0.34
     entendido
    -0.32
     Ganzen
    -0.32
    ください
    -0.31
     convient
    -0.30
     also
    -0.29
    incontro
    -0.29
    start
    -0.29
    POSITIVE LOGITS
    rungsseite
    0.88
     Италијани
    0.81
    ⟬
    0.73
     <>",
    0.72
     Administrativna
    0.71
    <unused51>
    0.68
    <unused68>
    0.68
     resourceCulture
    0.68
    <unused14>
    0.68
    [@BOS@]
    0.68
    Activations Density 0.147%

    No Known Activations